WO2016199662A1 - 画像情報処理システム - Google Patents

画像情報処理システム Download PDF

Info

Publication number
WO2016199662A1
WO2016199662A1 PCT/JP2016/066355 JP2016066355W WO2016199662A1 WO 2016199662 A1 WO2016199662 A1 WO 2016199662A1 JP 2016066355 W JP2016066355 W JP 2016066355W WO 2016199662 A1 WO2016199662 A1 WO 2016199662A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
image data
search
information
user
Prior art date
Application number
PCT/JP2016/066355
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
若林　和芳
Original Assignee
株式会社ウイル・コーポレーション
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社ウイル・コーポレーション filed Critical 株式会社ウイル・コーポレーション
Priority to US15/575,092 priority Critical patent/US20180157682A1/en
Priority to CN201680033786.4A priority patent/CN107636653A/zh
Priority to EP16807369.0A priority patent/EP3309694A4/de
Publication of WO2016199662A1 publication Critical patent/WO2016199662A1/ja

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5854—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using shape and object relationship
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/904—Browsing; Visualisation therefor

Definitions

  • the present invention relates to an image information processing system that retrieves the name and description of an object to be imaged on image data and provides it to a user.
  • the image search method and apparatus disclosed in Patent Document 1 can obtain information on an object from a captured image obtained by photographing an unknown object.
  • a subject name candidate is obtained by comparing a binarized image of a captured image of a subject with a binarized image for each item stored in the image database. Search from.
  • the captured image and the image can be captured even if the same subject is captured due to a difference in shooting conditions such as a difference in the season and time zone when the image was captured. Even if the images stored in the database are compared, there is a big difference in the search results. In order to take such differences into account, the ambiguity is increased in the similarity calculated from the comparison result to make it easy to obtain the search result, but the search accuracy is lowered.
  • the present invention is to provide an image information processing system.
  • the image information processing system of the present invention made to solve the above-described problems stores identification information including the name of the verification target object in association with the verification image data obtained by imaging the verification target object.
  • An image database an image acquisition unit that acquires image data, a search target input reception unit that receives selection of a search target from the image data acquired by the image acquisition unit, and a search target that is received by the search target input reception unit And image search processing for searching for image data for collation in which the object to be collated in which the similarity exceeds a reference value is calculated.
  • a display processing unit for displaying a search result including the search image data for comparison and the identification information on the display unit of the user information communication terminal, and a display unit of the user information communication terminal.
  • the selection input from the user for the indicated search result is received, and the image data acquired by the image acquisition unit is used as collation image data in association with the identification information of the search result received from the user.
  • a search result processing unit stored in the image database.
  • the search result processing unit uses, as collation image data, image data obtained by capturing a search object whose similarity exceeds a predetermined value set higher than the reference value.
  • the selection input from the user is received and stored in the image database in association with the identification information of the search result.
  • the image database includes attribute information including type information, shooting position information, and shooting time information corresponding to the matching image data obtained by capturing the matching object.
  • the search target input receiving unit receives input of the attribute information corresponding to the search target
  • the image search processing unit receives the input of the search target input receiving unit.
  • a matching image in which a matching degree between the attribute information corresponding to the object and the attribute information corresponding to the matching image data is calculated, and a matching target object whose matching degree exceeds the attribute reference value is captured.
  • Data is extracted, and the similarity between the search object received by the search object input receiving unit and the imaged object for verification of the extracted image data for verification is calculated, and the similarity exceeds the reference value.
  • Use object to be imaged is characterized by searching the image data for the verification imaged. With this configuration, the image data for matching with matching attribute information is extracted and the similarity is calculated, so that the search processing speed can be improved.
  • the image information processing system of the present invention can search the name of the object to be picked using the picked-up image with high search accuracy without knowing the name of the object to be picked up from the picked-up image taken by the user, for example.
  • FIG. 3 is a flowchart illustrating a processing process of the image information processing system according to the first embodiment.
  • 10 is a flowchart illustrating a processing process of the image information processing system according to the second embodiment.
  • 12 is a flowchart illustrating a processing process of the image information processing system according to the third embodiment. It is a figure which shows another example of the state as which the search result of this embodiment was displayed.
  • the image information processing system 1 of the present embodiment is realized using a computer including a server and the like.
  • the image information processing system 1 includes a computing device 30 such as a CPU that executes arithmetic processing of a program, a storage device 31 such as a RAM and a hard disk that stores information, and a display.
  • a display device 32 such as a display, an input device 33 such as a mouse, a keyboard, and a touch panel, and a communication device 34 that transmits and receives processing results of the arithmetic device 30 and information stored in the storage device 31 between computers. And have.
  • the means in the present invention are only logically distinguished from each other in function, and may be physically or virtually the same area.
  • these functions may be realized by one server, or each function may be distributed to two or more servers.
  • part or all of the functions of the present invention may be performed by the information communication terminal 20 such as a smartphone having a camera function used by the user.
  • the information communication terminal 20 may perform processing such as an image acquisition unit 12, a search target input reception unit 13, a display processing unit 15, and the like, which will be described later. Thereby, the processing load of the management server 10 can be reduced.
  • the management server 10 having each function of the image information processing system 1 can transmit and receive information via an information communication terminal 20 used by an administrator used by a user and a network such as the Internet.
  • the information communication terminal 20 includes, for example, a portable computer such as a personal computer, a mobile phone, a PHS, and a tablet computer in addition to a smartphone having a camera function.
  • the image information processing system 1 includes an image database 11, an image acquisition unit 12, a search target input reception unit 13, an image search processing unit 14, a display processing unit 15, and a search result processing unit 16.
  • the image database 11 stores identification information 100a including the name of the verification target image in association with the verification image data 100 obtained by capturing the verification target image as shown in FIG.
  • the verification image data 100 includes an image file of a natural landscape such as a flower, a bird, an animal and plant such as an insect, a bridge, a tower, a mountain, and a mountain. It consists of an image ID assigned to each image file.
  • the image database 11 stores attribute information 100b including type information, shooting position information, and shooting time information corresponding to the matching image data 100 obtained by shooting the matching target object in association with the identification information 100a. Also good.
  • the image acquisition unit 12 acquires the image data 2 from the information communication terminal 20 used by the user.
  • the file format of the image data 2 is not particularly limited.
  • the information communication terminal 20 is a smartphone having a camera function
  • the image data 2 captured by the user with the camera may be used.
  • the search target input receiving unit 13 receives selection of the search target 2a from the image data 2 acquired by the image acquisition unit 12.
  • the image data 2 is displayed on the display unit 21 including a liquid crystal display or the like of the information communication terminal 20, and the user searches the object to be imaged of the image data 2 by the user.
  • the user by means of tapping the object 2a, means for moving the selection window 3 as shown in FIG. 5 and surrounding the search object 2a, or a so-called in-camera provided on the display unit 21 side of the information communication terminal 20 Means for reading line-of-sight information directed to the search object 2a.
  • the search target input receiving unit 13 cuts out the portion of the received search target 2a, enlarges, rotates, and moves it, thereby easily calculating the similarity with the matching image data 100 stored in the image database 11.
  • the image data 2 may be converted so that
  • the search target input receiving unit 13 may receive input of attribute information corresponding to the search target 2a.
  • the attribute information corresponding to the search object 2a includes type information, shooting position information, shooting time information, and the like. Examples of the type information include “flowers”, “birds”, “insects”, “buildings”, “natural scenery”, and the like.
  • the shooting position information is information on a shooting location, and for example, the shooting position information may be acquired from a GPS device provided in the information communication terminal 20.
  • the shooting time information includes not only time information but also date information.
  • the image search processing unit 14 calculates the similarity between the search target 2a received by the search target input receiving unit 13 and the object to be verified of the verification image data 100 stored in the image database 11, and the similarity
  • the image data 100 for collation in which the object to be collated for which the reference value exceeds the reference value is retrieved.
  • a method for calculating the degree of similarity calculation is performed using a contour shape, a binarized image, a color distribution, and the like extracted by a known image processing technique.
  • the degree of similarity is calculated by setting 100% as the case where the search object 2a completely matches the object to be verified.
  • the image search processing unit 14 calculates the degree of coincidence between the attribute information corresponding to the search object 2 that the search target input receiving unit 13 has received and the attribute information 100b corresponding to the matching image data 100,
  • the image data 100 for comparison in which the object to be verified whose degree exceeds the attribute reference value is imaged is extracted, and for the comparison between the search object 2a received by the search object input receiving unit 13 and the extracted image data 100 for comparison
  • the degree of similarity with the object to be imaged is calculated, and the image data for matching 100 in which the object to be imaged for matching whose similarity exceeds the reference value is imaged is searched.
  • an attribute reference value may be set for each attribute information.
  • the attribute reference value of the type information may be perfectly matched.
  • the display processing unit 15 causes the display unit 21 of the information communication terminal 20 to display the searched image data for matching 100 and the identification information 100a as a search result 110.
  • the display processing unit 15 can display the search results 110 side by side in order from the highest similarity to the lowest. Furthermore, as shown in FIG. 6, the display processing unit 15 displays the search result 110 having a high similarity by visually recognizing the search result 110 by changing the display size of the search result 110 according to the similarity. Become.
  • the display processing unit 15 When the display processing unit 15 receives a selection input for the search result 200 displayed on the display unit 21 of the information communication terminal 20 from the user, as shown in FIG. 7, the verification imaging object and the verification imaging object Is displayed on the display unit 21 of the information communication terminal 20. Further, when receiving an input from the user to the registration button 111 displayed on the screen 110a, the display processing unit 15 determines whether to register the image data 2 displayed on the display unit 21 of the information communication terminal 20 illustrated in FIG. A screen that prompts you to enter a selection is displayed.
  • the search result processing unit 16 receives a selection input from the user for a screen that prompts a selection input as to whether or not to register the image data 2 displayed on the display unit 21 of the information communication terminal 20, and the image acquisition unit 12 acquires
  • the image data 2 is stored in the image database 11 as the verification image data 100 in association with the identification information 100a of the search result 110 that has received a selection input from the user.
  • the image data 2 is assigned an image ID for distinguishing the verification image data 100, and stored in the image database 11 in association with the identification ID of the identification information 100a.
  • the search result processing unit 16 limits the search object 2a whose similarity is higher than a reference value and exceeds a predetermined value to the captured image data 2, and selects the image data for verification 100 from the user.
  • the input may be stored in the image database 11 in association with the identification information 100a of the search result 110.
  • an unknown flower planted in a park or the like for example, is photographed using a smartphone camera having a camera function which is the information communication terminal 20 (S101), and the image data of “flowers” captured.
  • the process of displaying the identification information including the name of the flower from 2 will be described.
  • the image acquisition unit 12 acquires the image data 2 of “flower” captured by the information communication terminal 20 used by the user (S102). Note that the image data 2 may not be image data captured by the information communication terminal 20 used by the user, but may be image data 2 obtained via the Internet or the like.
  • the search target input receiving unit 13 receives the selection of the search target 2a from the image data 2 displayed on the display unit 21 of the information communication terminal 20 (S103). Then, the search target input receiving unit 13 cuts out the portion of the received search target 2a, enlarges, rotates, and moves it, thereby easily calculating the similarity with the matching image data 100 stored in the image database 11.
  • the image data 2 is converted so that
  • the method for accepting selection of the search target 2a is not particularly limited. For example, by tapping the search target 2a or moving the selection window 3 so as to surround the search target 2a as shown in FIG. The selection of the object 2a is accepted.
  • the image search processing unit 14 calculates the similarity between the search target 2a received by the search target input receiving unit 13 and the object to be checked stored in the image database 11 (S104).
  • a method for calculating the degree of similarity calculation is performed using a contour shape, a binarized image, a color distribution, or the like extracted by a known image processing technique.
  • the degree of similarity calculated in this way can be displayed as a numerical value, and the case where the search object 2a completely matches the object to be verified is 100%.
  • the image retrieval processing unit 14 retrieves the collation image data 100 in which the collation target object whose similarity exceeds the reference value is captured (S105).
  • the reference value can be changed as appropriate. For example, 80% may be set as the reference value.
  • the display processing unit 15 displays the search result 110 including the matching image data 100 and the identification information 100a on the display unit 21 of the information communication terminal 20 (S106).
  • the search results 110 are displayed side by side, for example, in the order from the search result 110 having a high similarity calculated by the image search processing unit 14 to the search result 110 having a low similarity. Further, the display processing unit 15 may display the search result 110 having a high similarity calculated as shown in FIG. 6 so as to have the largest display size.
  • the display processing unit 15 accepts a selection input to the search result 110 from the user, and performs information communication on the screen 110a configured by the verification object and the identification information 100a for the verification object illustrated in FIG. It is also possible to display on the display unit 21 of the terminal 20.
  • the display processing unit 15 When receiving the input of the registration button 111 shown in FIG. 7, the display processing unit 15 receives a selection input from the user for the search result 110 displayed on the display unit 21 of the information communication terminal 20, and the image data 2 shown in FIG. 8. Displays a screen that prompts the user to select whether or not to register.
  • the search result processing unit 16 displays the image acquired by the image acquisition unit 12.
  • Data 2 is stored in the image database 11 in association with the identification information 100a of the search result 110 that has received a selection input from the user as the verification image data 100 (S108).
  • the image data 2 is assigned an image ID for distinguishing the verification image data 100, and stored in the image database 11 in association with the identification ID of the identification information 100a.
  • the image data 2 is sequentially accumulated as the matching image data 100, and the accuracy of the calculated similarity is improved, so that the search accuracy can be improved, and a more accurate search result can be achieved. 110 can be provided.
  • the search result processing unit 16 When a Yes button is input on the screen for prompting selection of whether or not to register the image data 2 shown in FIG. 8, the search result processing unit 16 has exceeded the predetermined value set higher than the reference value. It is determined whether or not (S201). When the search result processing unit 16 determines that the similarity exceeds a predetermined value set higher than the reference value, the search result processing unit 16 selects and inputs the image data 2 of the search target object 2a as the matching image data 100 from the user. Is stored in the image database 11 in association with the identification information 100a of the search result 110 (S108).
  • the search accuracy can be further improved.
  • the search object 2a and all the imaged objects for comparison stored in the image database 11 are calculated, and when the calculated similarity exceeds a reference value, the similarity is high.
  • the search result 110 is displayed on the display unit 21 of the information communication terminal 20 used by the user.
  • an increase in the number of pieces of collation image data 100 causes a delay in processing speed in the similarity calculation process by the image search processing unit 14 and the management server 10 that executes the similarity calculation process.
  • the load will increase.
  • a case where the number of matching image data 100 for calculating the similarity is limited will be described with reference to a flowchart shown in FIG.
  • symbol is attached
  • the search target input receiving unit 13 receives not only the input of the search target 2a but also the input of attribute information corresponding to the search target 2a (S301). Since the search object 2a of this embodiment is “flower”, the type information accepts the selection of “flower”. In addition, input of shooting position information and shooting time information of the search object 2a may be accepted.
  • the shooting position information and the shooting time information are acquired from a GPS device and a date device provided in the information communication terminal 20, respectively.
  • the image search processing unit 14 matches the attribute information corresponding to the search target 2a received by the search target input receiving unit 13 with the attribute information 100b corresponding to the object to be checked stored in the image database 11. Is calculated (S302), and the object to be checked for matching whose degree of coincidence exceeds the attribute reference value is extracted (S303). For example, the degree of coincidence is calculated by setting 100% as the case where the attribute information of the search target 2a and the attribute information 100b of the object to be collated completely match.
  • the image search processing unit 14 calculates the similarity between the search target 2a and the extracted verification target object (S104), and the verification target image data of the verification target object whose similarity exceeds the reference value. 100 is searched (S105).
  • the type information of the attribute information corresponding to the search object 2a is “flowers”
  • the type information of the attribute information 100b is limited to the object to be collated set to “flowers”. Since the similarity is calculated, the search range is limited, and the processing speed is improved.
  • the shooting time information of the attribute information corresponding to the search object 2a corresponds to “daytime”
  • the shooting time information of the attribute information 100b is limited to the object to be verified set to “daytime”. Since similarities can be calculated between items having similar conditions, search accuracy can be improved.
  • the display processing unit 15 may cause the search result processing unit 16 to display the identification information 100 a associated with the image data 2 of the search target 2 a in the vicinity of the search target 2 a of the image data 2.
  • the search target input receiving unit 13 cuts out the search target object 2a
  • the search target input receiving unit 13 acquires coordinate position information with respect to the image data 2 of the search target object 2a.
  • the display processing unit 15 displays the identification information 100a associated with the image data 2 of the search target 2a by the search result processing unit 16 at a position that does not overlap with the coordinate position information.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Library & Information Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Processing Or Creating Images (AREA)
PCT/JP2016/066355 2015-06-10 2016-06-02 画像情報処理システム WO2016199662A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US15/575,092 US20180157682A1 (en) 2015-06-10 2016-06-02 Image information processing system
CN201680033786.4A CN107636653A (zh) 2015-06-10 2016-06-02 图像信息处理系统
EP16807369.0A EP3309694A4 (de) 2015-06-10 2016-06-02 Bildinformationsverarbeitungssystem

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2015117539A JP2017004252A (ja) 2015-06-10 2015-06-10 画像情報処理システム
JP2015-117539 2015-06-10

Publications (1)

Publication Number Publication Date
WO2016199662A1 true WO2016199662A1 (ja) 2016-12-15

Family

ID=57503568

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/066355 WO2016199662A1 (ja) 2015-06-10 2016-06-02 画像情報処理システム

Country Status (5)

Country Link
US (1) US20180157682A1 (de)
EP (1) EP3309694A4 (de)
JP (1) JP2017004252A (de)
CN (1) CN107636653A (de)
WO (1) WO2016199662A1 (de)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6873678B2 (ja) 2016-12-09 2021-05-19 キヤノン株式会社 画像処理装置、制御方法、及びプログラム
JP6904692B2 (ja) * 2016-12-09 2021-07-21 キヤノン株式会社 画像処理装置、制御方法、及びプログラム
JP6862164B2 (ja) 2016-12-09 2021-04-21 キヤノン株式会社 プログラム、画像処理装置、および画像処理方法
JP6862952B2 (ja) * 2017-03-16 2021-04-21 株式会社リコー 情報処理システム、情報処理装置、情報処理プログラム及び情報処理方法
CN111712807A (zh) * 2018-02-16 2020-09-25 麦克赛尔株式会社 便携信息终端、信息提示系统以及信息提示方法
JP7095338B2 (ja) * 2018-03-19 2022-07-05 株式会社リコー 画像検索装置、情報処理システムおよび画像検索方法
WO2019181923A1 (ja) * 2018-03-23 2019-09-26 住友重機械工業株式会社 建設機械の支援装置
JP2020035086A (ja) * 2018-08-28 2020-03-05 富士ゼロックス株式会社 情報処理システム、情報処理装置およびプログラム
JP7087844B2 (ja) * 2018-08-31 2022-06-21 トヨタ自動車株式会社 画像処理装置、画像処理システム及び車両
US20220147050A1 (en) * 2020-11-10 2022-05-12 Meteorolite Ltd. Methods and devices for operating an intelligent mobile robot

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010218372A (ja) * 2009-03-18 2010-09-30 Olympus Corp サーバシステム、端末装置、プログラム、情報記憶媒体及び画像検索方法
WO2013175608A1 (ja) * 2012-05-24 2013-11-28 株式会社日立製作所 画像解析装置、画像解析システム、画像解析方法

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4074366B2 (ja) * 1998-02-24 2008-04-09 コニカミノルタビジネステクノロジーズ株式会社 画像検索装置及び方法並びに画像検索プログラムを記録した記録媒体
US20050076004A1 (en) * 2003-09-30 2005-04-07 Hiroyuki Yanagisawa Computer, database generating method for electronic picture book service, photographed subject information providing method, recording medium, and computer data signal
US7872669B2 (en) * 2004-01-22 2011-01-18 Massachusetts Institute Of Technology Photo-based mobile deixis system and related techniques
US20070133947A1 (en) * 2005-10-28 2007-06-14 William Armitage Systems and methods for image search
US7783085B2 (en) * 2006-05-10 2010-08-24 Aol Inc. Using relevance feedback in face recognition
US7844591B1 (en) * 2006-10-12 2010-11-30 Adobe Systems Incorporated Method for displaying an image with search results
JP2008146602A (ja) * 2006-12-13 2008-06-26 Canon Inc 文書検索装置、文書検索方法、プログラム及び記憶媒体
WO2008152805A1 (ja) * 2007-06-14 2008-12-18 Panasonic Corporation 画像認識装置及び画像認識方法
US8131118B1 (en) * 2008-01-31 2012-03-06 Google Inc. Inferring locations from an image
US8190623B2 (en) * 2008-06-05 2012-05-29 Enpulz, L.L.C. Image search engine using image analysis and categorization
US8483715B2 (en) * 2009-03-26 2013-07-09 Yahoo! Inc. Computer based location identification using images
US8332429B2 (en) * 2010-06-22 2012-12-11 Xerox Corporation Photography assistant and method for assisting a user in photographing landmarks and scenes
US8782077B1 (en) * 2011-06-10 2014-07-15 Google Inc. Query image search
US9171018B2 (en) * 2012-01-17 2015-10-27 Google Inc. System and method for associating images with semantic entities
KR102059913B1 (ko) * 2012-11-20 2019-12-30 삼성전자주식회사 태그 정보 저장 방법 및 장치와 태그 정보를 이용한 이미지 검색 방법 및 장치
US9424279B2 (en) * 2012-12-06 2016-08-23 Google Inc. Presenting image search results
JP6064618B2 (ja) * 2013-01-23 2017-01-25 富士ゼロックス株式会社 情報処理装置及びプログラム
US20150227780A1 (en) * 2014-02-13 2015-08-13 FacialNetwork, Inc. Method and apparatus for determining identity and programing based on image features
JP6435779B2 (ja) * 2014-10-30 2018-12-12 富士ゼロックス株式会社 情報処理装置及び情報処理プログラム

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010218372A (ja) * 2009-03-18 2010-09-30 Olympus Corp サーバシステム、端末装置、プログラム、情報記憶媒体及び画像検索方法
WO2013175608A1 (ja) * 2012-05-24 2013-11-28 株式会社日立製作所 画像解析装置、画像解析システム、画像解析方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3309694A4 *

Also Published As

Publication number Publication date
EP3309694A4 (de) 2018-12-05
JP2017004252A (ja) 2017-01-05
EP3309694A1 (de) 2018-04-18
US20180157682A1 (en) 2018-06-07
CN107636653A (zh) 2018-01-26

Similar Documents

Publication Publication Date Title
WO2016199662A1 (ja) 画像情報処理システム
US9076069B2 (en) Registering metadata apparatus
US8977055B2 (en) Information processing device, object recognition method, program, and terminal device
US9222783B2 (en) Location estimation using image analysis
US11335087B2 (en) Method and system for object identification
WO2016015437A1 (zh) 图片搜索库的生成及图片搜索方法、装置和设备
Chen et al. Building book inventories using smartphones
US20140193077A1 (en) Image retrieval apparatus, image retrieval method, query image providing apparatus, query image providing method, and program
US20120310968A1 (en) Computer-Vision-Assisted Location Accuracy Augmentation
JP5563494B2 (ja) 対応参照画像検索装置及び方法、コンテンツ重畳装置、システム、及び方法、並びにコンピュータプログラム
CN102521365A (zh) 空间图像索引和关联的更新功能
JP2007206772A (ja) 端末装置及びサーバー及びランドマーク名検索システム及び検索プログラム
US20170039450A1 (en) Identifying Entities to be Investigated Using Storefront Recognition
JP5223034B2 (ja) 情報提供装置、情報提供方法、情報提供処理プログラム、及び情報提供処理プログラムを記録した記録媒体
JP6607987B2 (ja) 情報提供システム、サーバ装置、及び情報提供方法
KR20190124436A (ko) 영상 기반 건물 검색 방법 및 장치
KR20130038547A (ko) 관심영역 설정을 이용한 이미지 이중 검색 시스템
JP6591594B2 (ja) 情報提供システム、サーバ装置、及び情報提供方法
US9064020B2 (en) Information providing device, information providing processing program, recording medium having information providing processing program recorded thereon, and information providing method
JP5932107B2 (ja) 画像処理サーバ及び撮像装置
JP2007041762A5 (de)
JP6244887B2 (ja) 情報処理装置、画像探索方法、及びプログラム
KR20150106621A (ko) 단말, 서비스 제공 장치, 그 제어 방법, 컴퓨터 프로그램이 기록된 기록 매체 및 이미지 검색 시스템
KR101810533B1 (ko) 영상인식 기술을 이용한 지도 서비스에 관심 지점 입력 장치 및 방법
JP2009042962A (ja) 検索システム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16807369

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15575092

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016807369

Country of ref document: EP